Generative Agents: Interactive Simulacra of Human Behavior

Re:Generative Agents: Interactive Simulacra of Human Behavior by og_kalu on Tuesday April 11, 2023 @12:32AM (#35520868)

for me, an unsupervised pipeline is not handholding. the thoughts drive actions. If you can't control how those thoughts form or process memories then i don't see what is hand holding about it. a pipeline is one and done.

[ Parent | on HN ]

Re:Generative Agents: Interactive Simulacra of Human Behavior by Imnimo on Tuesday April 11, 2023 @12:36AM (#35520901)

I would say that if you have to direct the steps of the agent's thought process:

-Generate tests

-Run tests (performed automatically)

-Gather results (performed automatically)

-Evaluate results, branch to either accept or refine

-Generate refinements

etc., then that's hand-holding. It's task specific reasoning that the agent can't perform on its own. It presents a big obstacle to extending the agent to more complex domains, because you'd have to hand-implement a new guided thought process for each new domain, and as the domains become more complex, so do the necessary thought processes.

[ Parent | on HN ]

Re:Generative Agents: Interactive Simulacra of Human Behavior by og_kalu on Tuesday April 11, 2023 @01:04AM (#35521059)

The pipeline doesn't really have to be task/domain specific.

[ Parent | on HN ]

Re:Generative Agents: Interactive Simulacra of Human Behavior by nuancebydefault on Tuesday April 11, 2023 @05:27PM (#35531815)

You can call it handholding. Or call it having control over the direction of 'thought' of the LLM. you can train another LLM that creates handholding pipeline steps. Then LLM squared can be tagged new LLM.

[ Parent | on HN ]